An e-commerce recommendation method based on self-attention mechanism and graph neural network

Abstract

The invention provides a self-attention mechanism and a graph neural network e-commerce recommendation method. Firstly, the e-commerce transaction data is preprocessed, the sessions that meet the requirements are extracted, and the sequence and label are generated to form the data set used in the experiment; according to the data set obtained by the preprocessing, the session graph is formed and the weight is normalized, and then input to In the graph neural network, the vector representation of the nodes in the graph is obtained; finally, the local interest vector representation and the global vector representation are extracted from the vector representation of the nodes in the graph, and then the self-attention mechanism is used for the local interest vector representation and the global vector representation respectively to obtain the corresponding local The self-attention vector and the global self-attention vector are aggregated to obtain a vector representation of mixed interest, which is used to recommend high-scoring items to users. The present invention fully considers the related information of the user's past clicks, and provides a recommendation method with better effect.

Description

technical field [0001] The invention belongs to the technical field of personalized recommendation in data mining applications, and in particular relates to a self-attention mechanism and a graph neural network e-commerce recommendation method. Background technique [0002] At present, in the era of massive data, accompanied by the problem of information cocoons for users, how to provide effective personalized recommendation results based on the user's historical data is an important problem to be solved. Using scientific and effective methods to mine data to extract user interests and generate a suitable personalized recommendation system is the main means to solve this problem. [0003] The difference from the above is that the historical user behavior data in actual work is often too long, but in the face of massive data, low latency, and limited computing resources, the recommendation algorithm has to be established in a short session, but At the same time, the extracti...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the shortcomings of not making full use of the user portrait and the user's past information, and the inaccurate extraction of the conversion relationship between the item and the item in the conversation graph. Accurate capture, better access to the conversion relationship between items, and effectively extract the user's interest preferences

Images